{"total":98,"rows":[{"id":"2410.06703","title":"ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents","created":"2024-10-09","cited_by_count":133,"area":"agents"},{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124,"area":null},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2410.13788","title":"Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions","created":"2024-10-17","cited_by_count":76,"area":null},{"id":"2503.22674","title":"QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?","created":"2025-03-28","cited_by_count":63,"area":"lr"},{"id":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47,"area":"alignment"},{"id":"2505.10831","title":"Creating General User Models from Computer Use","created":"2025-05-16","cited_by_count":44,"area":null},{"id":"2511.08798","title":"Structured Uncertainty guided Clarification for LLM Agents","created":"2025-11-11","cited_by_count":41,"area":"agents"},{"id":"2502.13069","title":"Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering","created":"2025-02-18","cited_by_count":38,"area":"agents"},{"id":"2505.13360","title":"What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts","created":"2025-05-19","cited_by_count":32,"area":null},{"id":"2505.22655","title":"Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents","created":"2025-05-28","cited_by_count":32,"area":"agents"},{"id":"2503.13975","title":"Navigating Rifts in Human-LLM Grounding: Study and Benchmark","created":"2025-03-18","cited_by_count":29,"area":null},{"id":"2506.08500","title":"DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs","created":"2025-06-10","cited_by_count":25,"area":"rag"},{"id":"2409.08775","title":"What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use","created":"2024-09-13","cited_by_count":24,"area":null},{"id":"2404.12447","title":"AmbigDocs: Reasoning across Documents on Different Entities under the Same Name","created":"2024-04-18","cited_by_count":21,"area":null},{"id":"2502.21239","title":"Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMs","created":"2025-02-28","cited_by_count":20,"area":null},{"id":"2507.23158","title":"User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal","created":"2025-07-30","cited_by_count":19,"area":null},{"id":"2603.26233","title":"Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents","created":"2026-03-27","cited_by_count":19,"area":"agents"},{"id":"2405.12059","title":"STYLE: Improving Domain Transferability of Asking Clarification Questions in Large Language Model Powered Conversational Agents","created":"2024-05-20","cited_by_count":17,"area":"agents"},{"id":"2602.16699","title":"Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents","created":"2026-02-18","cited_by_count":17,"area":"agents"},{"id":"2410.04241","title":"Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations","created":"2024-10-05","cited_by_count":15,"area":null},{"id":"2411.00927","title":"ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents","created":"2024-11-01","cited_by_count":15,"area":"wm"},{"id":"2606.28733","title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","created":"2026-06-27","cited_by_count":15,"area":"agents"},{"id":"2503.01940","title":"AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification","created":"2025-03-03","cited_by_count":13,"area":"agents"},{"id":"2512.21120","title":"ClarifyMT-Bench: Benchmarking and Improving Multi-Turn Clarification for Conversational Large Language Models","created":"2025-12-24","cited_by_count":13,"area":null},{"id":"2402.19471","title":"Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Sampling","created":"2024-02-29","cited_by_count":12,"area":null},{"id":"2411.07237","title":"Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries","created":"2024-11-11","cited_by_count":12,"area":null},{"id":"2504.16939","title":"A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions","created":"2025-04-07","cited_by_count":9,"area":"agents"},{"id":"2506.04089","title":"AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2510.20886","title":"Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People","created":"2025-10-23","cited_by_count":9,"area":"agents"},{"id":"2412.01250","title":"Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues","created":"2024-12-02","cited_by_count":8,"area":"agents"},{"id":"2412.13835","title":"RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs","created":"2024-12-18","cited_by_count":8,"area":null},{"id":"2510.08517","title":"CaRT: Teaching LLM Agents to Know When They Know Enough","created":"2025-10-09","cited_by_count":7,"area":"agents"},{"id":"2411.17993","title":"DRS: Deep Question Reformulation With Structured Output","created":"2024-11-27","cited_by_count":6,"area":null},{"id":"2505.12543","title":"Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey","created":"2025-05-18","cited_by_count":6,"area":"agents"},{"id":"2602.03429","title":"DiscoverLLM: From Executing Intents to Discovering Them","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2602.10525","title":"LHAW: Controllable Underspecification for Long-Horizon Tasks","created":"2026-02-11","cited_by_count":6,"area":null},{"id":"2607.01236","title":"Safeguarding LLM Agents from Misalignment through Provenance Analysis","created":"2026-05-01","cited_by_count":6,"area":"agents"},{"id":"2507.10445","title":"Referential ambiguity and clarification requests: comparing human and LLM behaviour","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2512.04068","title":"Learning Steerable Clarification Policies with Collaborative Self-play","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2605.09698","title":"Ambig-DS: A Benchmark for Task-Framing Ambiguity in Data-Science Agents","created":"2026-05-10","cited_by_count":5,"area":"agents"},{"id":"2604.14624","title":"Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks","created":"2026-04-16","cited_by_count":4,"area":null},{"id":"2404.08424","title":"Comparing Apples to Oranges: LLM-powered Multimodal Intention Prediction in an Object Categorization Task","created":"2024-04-12","cited_by_count":3,"area":null},{"id":"2407.12061","title":"Situated Instruction Following","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2502.07132","title":"Interactive Data Harmonization with LLM Agents: Opportunities and Challenges","created":"2025-02-10","cited_by_count":3,"area":"agents"},{"id":"2512.03381","title":"Characterizing Language Use in a Collaborative Situated Game","created":"2025-12-03","cited_by_count":3,"area":null},{"id":"2601.16400","title":"Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification","created":"2026-01-23","cited_by_count":3,"area":"agents"},{"id":"2604.27093","title":"Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations","created":"2026-04-29","cited_by_count":3,"area":"alignment"},{"id":"2605.30251","title":"Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models","created":"2026-05-28","cited_by_count":3,"area":"distill"},{"id":"2412.15683","title":"Variability Need Not Imply Error: The Case of Adequate but Semantically Distinct Responses","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2506.20876","title":"Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2507.03336","title":"Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky","created":"2025-07-04","cited_by_count":2,"area":"agents"},{"id":"2601.07820","title":"Reference Games as a Testbed for the Alignment of Model Uncertainty and Clarification Requests","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2605.24432","title":"Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2608.10430","title":"Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique","created":"2026-08-11","cited_by_count":2,"area":"agents"},{"id":"2608.19564","title":"Remember, Verify, or Ask? Cross-Family Evaluation of Memory Commitment in LLM Agents","created":"2026-08-20","cited_by_count":2,"area":"agents"},{"id":"2505.21757","title":"BehaviorSFT: Behavioral Token Conditioning for Clinical Agents Across the Proactivity Spectrum","created":"2025-05-27","cited_by_count":1,"area":"agents"},{"id":"2506.07448","title":"Extending Epistemic Uncertainty Beyond Parameters Would Assist in Designing Reliable LLMs","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2509.14456","title":"Correct-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMs","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2509.22750","title":"MARCH: Evaluating the Intersection of Ambiguity Interpretation and Multi-hop Inference","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2512.13478","title":"NRR-Core: Non-Resolution Reasoning as a Computational Framework for Contextual Identity and Ambiguity Preservation","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2601.02643","title":"AWARE-US: Preference-Aware Infeasibility Resolution in Tool-Calling Agents","created":"2026-01-06","cited_by_count":1,"area":"agents"},{"id":"2602.11938","title":"Who is the richest club in the championship? Detecting and Rewriting Underspecified Questions Improve QA Performance","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2602.17022","title":"ReIn: Conversational Error Recovery with Reasoning Inception","created":"2026-02-19","cited_by_count":1,"area":"lr"},{"id":"2605.17324","title":"ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2605.25831","title":"Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2607.13594","title":"SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing","created":"2026-07-15","cited_by_count":1,"area":"agents"},{"id":"2607.16412","title":"Interactive Task Alignment as a POMDP","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2607.21143","title":"One More Turn, Less Regret: A Regret-Based Multi-Turn Benchmark for LLMs' Clarification Policies","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2608.17605","title":"Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2608.27818","title":"AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics","created":"2026-08-28","cited_by_count":1,"area":"agents"},{"id":"2609.12373","title":"Toward Robust Personalized Alignment for LLMs: Mitigating Persona Drift in Multi-Turn Dialogue","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2609.30706","title":"LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2503.20791","title":"ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2506.16288","title":"Next-Token Prediction Should be Ambiguity-Sensitive: A Meta-Learning Perspective","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2512.13154","title":"MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2601.19933","title":"NRR-Phi: A Typed External Text-to-State Interface and Update Contract for Inspectable Ambiguity-State Maintenance","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2602.07796","title":"Thinking Is Not Telling: Information Disclosure in User-Service LLM Agents","created":"2026-02-08","cited_by_count":0,"area":"lr"},{"id":"2604.00414","title":"Decision-Centric Design for LLM Systems","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.03924","title":"Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2604.18122","title":"Decisive: Guiding User Decisions with Optimal Preference Elicitation from Unstructured Documents","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.25204","title":"Clarification Is Not Enough: Post-Clarification Answering Remains the Bottleneck in Multi-Turn QA","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2607.26611","title":"Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.00215","title":"Personalizing Large Language Model Agents with Small Policy Models","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2608.03177","title":"Diversity is Not Ambiguity: Toward Accurate and Efficient Ambiguity Detection for Open-Domain QA","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.13577","title":"AI Evaluation Should Work With Humans","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.21721","title":"Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2608.26700","title":"PragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgments","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.05258","title":"Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.20684","title":"HerHealthEval: Evaluating Multilingual and Register-Sensitive Understanding of Women's Health Communication","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22249","title":"A Tutorial on Prompt Engineering: From Messy Thoughts to AI Workflows","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.32255","title":"Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33885","title":"Prospective Interpretation Risk: Principled Communication Control Between LLMs","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.01769","title":"CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.04089","title":"Pareto-Dominant Clarification: Post-Training Coding LLMs via PPO-Lagrangian Budget Constraints","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.12655","title":"CLEAT: Learning Value-Guided Clarification for Interactive Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.19138","title":"MA-Bench: Measuring Operational Planning in Language Models","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20052","title":"What Is a Clarification? Estimating Model-Dependent Input Ambiguity","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}